Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GPT-OCR

Introduction

GPT-OCR is an easy-to-use command line interface tool to quickly read text from any *.jpg/png image using OpenAI's GPT4-Vision-Preview model. Available for Windows and Linux and can be used either standalone or integrated into other processes.

Installation

Prerequisites

  • Windows or Linux Operating System
  • OpenAI API Key

How to use

Download the binary here and execute it via command line. Usage:

gpt-ocr.exe --input (path to the image) --apikey (openai api key)

The --apikey flag can be omitted by setting the environment variable OCR_APIKEY

About

A simple CLI tool to read text from images using GPT 4 for WIndows and Linux

Resources

Stars

Watchers

Forks

Releases

Packages

Used by

Contributors

Languages